VOOZH about

URL: https://willitrunai.com/can-run/aya-expanse-32b-on-arc-pro-b60-24gb

⇱ Aya Expanse 32B on Intel Arc Pro B60 24GB? YES

Can Aya Expanse 32B run on Intel Arc Pro B60 24GB?

YES — With Offload

C52Usable
○Estimated from fit model

Aya Expanse 32B needs ~25.3 GB VRAM. Intel Arc Pro B60 24GB has 24.0 GB. With Q4_K_M quantization, expect ~9 tok/s.

Runtime: llama.cppCapacity: OffloadBandwidth: MediumStack: StandardBottleneck: Balanced
Share:

Operating mode

Choose the run profile you care about

Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.

Current mode

Balanced

Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 25.3 GB, 9.4 tok/s, Runs with offload (needs ~1 GB host RAM)
25.3 GB required24.0 GB available
105% VRAM needed

1.3 GB over capacity — needs offload or smaller quantization

Fit status

Runs with offload (needs ~1 GB host RAM)

Decode

9.4 tok/s

TTFT

20487 ms

Safe context

8K

Memory

25.3 GB / 24.0 GB

Memory breakdown

Weights19.5 GB
KV Cache2.4 GB
Runtime0.9 GB
Headroom2.4 GB

See how fast it feels

See how fast it feelsAya Expanse 32B on Intel Arc Pro B60 24GB
1st promptCold start — includes initialization
>What is local AI inference?
Local AI inference means running an AI language model directly on your own hardware — your laptop, desktop, or server — instead of sending requests to a remote cloud API. When you run inference locally the model weights are loaded into your GPU or unified memory. Each token you generate requires reading those weights from memory, so memory bandwidth is the main bottleneck for decode speed. Key benefits of running locally: - Full privacy: your prompts never leave your machine - No per-token cost or rate limits - Works offline once the model is downloaded - Latency depends only on your hardware
2nd promptWarm — model ready, no init overhead
>How much VRAM do I need?
It depends on the model size and quantization level. A rough rule of thumb: Model size Q4 (4-bit) Q8 (8-bit) FP16 7B params ~4.3 GB ~7.5 GB ~14 GB 13B params ~7.9 GB ~13.9 GB ~26 GB 70B params ~42.7 GB ~74.9 GB ~140 GB Most people use 4-bit quantization (Q4_K_M) which gives 90-95% of full quality at a fraction of the memory. A 24 GB GPU can comfortably run most 7B-13B models.
Estimated: 9.4 tok/s decode · 20.5s TTFT (warm) · 24 tok/s prefill

What limits this setup

The raw memory story may look fine, but the software ecosystem is still a constraint here.

Very little memory headroom

You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.

Runtime ecosystem is narrower than CUDA

Intel GPUs can look attractive on memory per dollar, but local AI tooling, kernels, and model coverage are still broader and easier on CUDA today.

Best improvement path

Prefer CUDA if you want the path of least resistance

If your goal is maximum runtime coverage, easier troubleshooting, and better support for new local AI releases, CUDA is usually still the safer upgrade path.

Buy headroom, not only minimum fit

A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.

Performance by workload

WorkloadGradeFitDecodeTTFTContext
ChatCRuns with offload (needs ~0 GB host RAM)10.5 tok/s10101 ms8K
CodingCRuns with offload (needs ~1 GB host RAM)9.4 tok/s20487 ms8K
Agentic CodingCVery compromised (needs ~2.6 GB host RAM)7.8 tok/s35971 ms8K
ReasoningCRuns with offload (needs ~1 GB host RAM)9.4 tok/s24212 ms8K
RAGCVery compromised (needs ~2.6 GB host RAM)7.8 tok/s44963 ms8K

Quantization options

How Aya Expanse 32B (32B params) fits at each quantization level on Intel Arc Pro B60 24GB (24.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
12.5 GB
LowB56
Q3_K_S
3
15.7 GB
LowB55
NVFP4Best for your GPU
4
17.9 GB
MediumC55
Q4_K_M
4
19.5 GB
MediumF0
Q5_K_M
5
23.0 GB
HighF0
Q6_K
6
26.2 GB
HighF0
Q8_0
8
34.2 GB
Very HighF0
F16
16
65.6 GB
MaximumF0

Get started

Copy-paste commands to run Aya Expanse 32B on your machine.

Run

ollama run aya-expanse:32b

Upgrade options

Hardware that runs Aya Expanse 32B well

👁 NVIDIA
NVIDIA A100 40GBBiggest leap
40 GB VRAM (+16)1555 GB/s (+1099)
B
Raises estimated decode speed by about 674%.72.8 tok/s decode

Raises estimated decode speed by about 674%.

Adds memory headroom for longer context windows and future model growth.

This is not only a hardware jump. It also gives you a cleaner runtime ecosystem for local LLM tooling.

~$10,000 MSRP

👁 Intel
Intel Data Center GPU Max 1550 128GBBudget pick
128 GB VRAM (+104)3200 GB/s (+2744)
C
Raises estimated decode speed by about 1095%.112.3 tok/s decode

Raises estimated decode speed by about 1095%.

Adds memory headroom for longer context windows and future model growth.

~$15,000 MSRP

👁 Intel
Gaudi 3 128GBBest value
128 GB VRAM (+104)3700 GB/s (+3244)
C
Raises estimated decode speed by about 1435%.144.3 tok/s decode

Raises estimated decode speed by about 1435%.

Adds memory headroom for longer context windows and future model growth.

~$15,000 MSRP

Frequently asked questions

See all results for Intel Arc Pro B60 24GBSee all hardware for Aya Expanse 32B